Model Releases
DeepSeek-V4-Flash-0731 is Ollama's fastest growing model ever in token usage. We are scaling capacity in US & Europe. On Ollama, this model …
DeepSeek-V4-Flash-0731 is Ollama's fastest growing model ever in token usage. We are scaling capacity in US & Europe. On Ollama, this model runs with high performance (100tps+) and zero data retention
DeepSeek-V4-Flash-0731 is Ollama's fastest growing model ever in token usage. We are scaling capacity in US & Europe. On Ollama, this model runs with high performance (100tps+) and zero data retention. Your data stays yours. ollama run deepseek-v4-flash:0731-cloud
Related
- DeepSeek-V4-Flash-0731 is now over 2x faster than yesterday on Ollama's cloud!
- deepseek-v4-flash is now available on Ollama's cloud! Hosted in the US. Try it with Claude Code: ollama launch claude --model deepseek-v4-fl…
- DeepSeek-V4-Flash-0731 is now available on Ollama's cloud. This update substantially enhances the model's agentic capabilities: ollama run d…
- Model page for more information and integrations: https://ollama.com/library/deepseek-v4-flash
Source: Ollama (X) | 2026-08-04